Can accurate demographic information about people who use prescription medications nonmedically be derived from Twitter?

• Type of Material: Article
• Authors: Yuan-ChiC Yang, Emory University; Mohammed A Al-Garadi, Emory University; Jennifer S Love, Icahn School of Medicine at Mount Sinai; Hannah Cooper, Emory University; Jeanmarie Perrone, University of Pennsylvania Perelman School of Medicine; Abeed Sarker, Emory University
• Language: English
• Date: 2023-02-21
• Publisher: PNAS
• Publication Version: Final Published Version
• Copyright Statement: © 2023 the Author(s). Published by PNAS.
• License: Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International
• Final Published Version (URL): http://dx.doi.org/10.1073/pnas.2207391120
• Title of Journal or Parent Work: Proceedings of the National Academy of Sciences of the United States of America
• Volume: 120
• Issue: 8
• Start Page: e2207391120
• End Page: e2207391120
• Keywords: natural language processing; Twitter; toxicovigilance; Prescriptions; Demography; Central Nervous System Stimulants; Social Media; Substance-Related Disorders; Humans; machine learning; substance use
• Research Categories: Psychology, Behavioral; Health Sciences, Medicine and Surgery; Engineering, Biomedical

Abstract

Traditional substance use (SU) surveillance methods, such as surveys, incur substantial lags. Due to the continuously evolving trends in SU, insights obtained via such methods are often outdated. Social media-based sources have been proposed for obtaining timely insights, but methods leveraging such data cannot typically provide fine-grained statistics about subpopulations, unlike traditional approaches. We address this gap by developing methods for automatically characterizing a large Twitter nonmedical prescription medication use (NPMU) cohort (n = 288,562) in terms of age-group, race, and gender. Our natural language processing and machine learning methods for automated cohort characterization achieved 0.88 precision (95% CI:0.84 to 0.92) for age-group, 0.90 (95% CI: 0.85 to 0.95) for race, and 94% accuracy (95% CI: 92 to 97) for gender, when evaluated against manually annotated gold-standard data. We compared automatically derived statistics for NPMU of tranquilizers, stimulants, and opioids from Twitter with statistics reported in the National Survey on Drug Use and Health (NSDUH) and the National Emergency Department Sample (NEDS). Distributions automatically estimated from Twitter were mostly consistent with the NSDUH [Spearman r: race: 0.98 (P < 0.005); age-group: 0.67 (P < 0.005); gender: 0.66 (P = 0.27)] and NEDS, with 34/65 (52.3%) of the Twitter-based estimates lying within 95% CIs of estimates from the traditional sources. Explainable differences (e.g., overrepresentation of younger people) were found for age-group-related statistics. Our study demonstrates that accurate subpopulation-specific estimates about SU, particularly NPMU, may be automatically derived from Twitter to obtain earlier insights about targeted subpopulations compared to traditional surveillance approaches.